A recent study published on arXiv investigates the phenomenon of Neural Collapse within the context of ordinal regression models in deep learning. This research introduces the Unconstrained Feature Model as a theoretical framework designed to better understand the behavior of neural networks exhibiting Neural Collapse. Neural Collapse, a pattern observed in the final layers of deep networks during training, has been confirmed to occur specifically in ordinal regression tasks, as supported by the study's analysis. The Unconstrained Feature Model was introduced with the explicit purpose of providing insights into this phenomenon, addressing a gap in the theoretical understanding of neural network behavior in ordinal regression settings. This work contributes to ongoing efforts in the machine learning community to characterize and explain emergent behaviors in deep learning models. The study's findings align with previous observations of Neural Collapse in classification tasks, extending the concept to ordinal regression. Overall, the research offers a novel perspective by combining empirical evidence with theoretical modeling to advance knowledge in this area.